adelusioluwatosin/Spatiotemporal-and-Machine-Learning-Based-Prediction-of-Tropospheric-Formaldehyde-In-Nigeria

Domaine:

environment and energyclimate

Type de record:

projectmodel

Créateur:

ade

Hôte:

Spatiotemporal and Machine Learning-Based Prediction of Tropospheric Formaldehyde in Nigeria # Spatiotemporal Analysis of Formaldehyde (HCHO) over Nigeria (2019–2025) and Machine Learning Forecasting (2026–2030) An undergraduate research dissertation codebase performing spatiotemporal characterization, hotspot detection, meteorological/fire driver attribution, machine learning predictive modeling, and a 5-year spatial forecast (2026–2030) of tropospheric Formaldehyde (HCHO) column densities over Nigeria. --- ## 📌 Executive Summary Tropospheric Formaldehyde (HCHO) is a primary indicator of volatile organic compound (VOC) emissions, air pollution, and precursor activity for ground-level ozone. This project leverages **Sentinel-5P TROPOMI satellite data (2019–2025)** combined with **NASA MERRA-2 reanalysis meteorology** and **MODIS FIRMS biomass burning data** across Nigeria's ecological zones. ### Key Headline Results: - **Study Horizon:** 84 monthly grids (2019–2025) at $0.1^\circ \times 0.1^\circ$ spatial resolution across Nigeria. - **Top Machine Learning Model:** **LightGBM** achieved the highest test performance (**$R^2 = 0.841$**, RMSE $= 0.142 \times 10^{-4} \text{ mol/m}^2$) on the 2025 hold-out year, beating the seasonal Climatology Baseline ($R^2 = 0.832$). - **Key Atmospheric Drivers:** Temperature at 2m (`T2M`) and Fire Radiative Power (`FRP`) were identified as primary drivers explaining dry-season HCHO peaks. - **5-Year Spatial Forecast:** 60 monthly spatial grids generated for **2026 to 2030** using a recursive multi-step machine learning ensemble. - **Independent Cross-Satellite Validation:** Validated against independent **OMI (Aura)** satellite sensor observations ($r = 0.258$, 16 overlapping months). --- ## 🎯 Research Objectives | Obj | Scope | Key Findings / Highlights | |---|---|---| | **1. Spatiotemporal Analysis** | Monthly & seasonal trend characterization (2019–2025) | Strong dry-season peaks; highest concentrations localized over southern industrial/oil-producing regions. | | **2. Hotspot Detection** | Getis-Ord $G_i^*$ …

Visit

github.com

Similaires

Machine learning-based model for prediction of accountants behaviour in NigeriaMachine Learning-Based Prediction of Construction Project Delays in Public Building Projects in NigeriaMachine Learning-Based Prediction of Malaria Risk Among Rural Households in Kebbi State, NigeriaMachine Learning-Based Prediction of Household Energy Consumption in GhanaA Machine Learning-Based Prediction of Malaria Occurrence in KenyaMachine learning models application for spatiotemporal patterns of particulate matter prediction and forecasting over Morocco in north of Africa

Machine learning-based model for prediction of accountants behaviour in Nigeria

The integration of technology in accounting roles raises questions about the adaptability and skills

Machine Learning-Based Prediction of Construction Project Delays in Public Building Projects in Nigeria

Construction project delays remain one of the major challenges affecting the successful delivery of

Machine Learning-Based Prediction of Malaria Risk Among Rural Households in Kebbi State, Nigeria

Malaria remains a major public health burden in rural sub-Saharan Africa, where environmental and so

Machine Learning-Based Prediction of Household Energy Consumption in Ghana

Abstract Accurate forecasting of residential electricity demand is a pressing issu

A Machine Learning-Based Prediction of Malaria Occurrence in Kenya

For many years’ malaria has been a health public concern in Kenya as well as many parts of Africa an